Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating partiality or slight changes in conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Partial or slight occurrence

    np_acts-logits-general · gemini-2.0-flash

    partial, slight, or vague indication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समीक्षक
    -0.59
     meticulously
    -0.49
     Simply
    -0.48
    />";
    -0.47
    毅
    -0.47
     kepad
    -0.46
     Wit
    -0.46
    usiai
    -0.46
    ,))
    -0.45
    /");
    -0.45
    POSITIVE LOGITS
    ではある
    0.83
     hinting
    0.81
     hint
    0.80
     semblance
    0.78
     hinted
    0.76
     hints
    0.72
     בלב
    0.71
    ながらも
    0.69
     resemblance
    0.68
     but
    0.68
    Act Density 0.394%

    No Known Activations